Back to search results
Ministral-3-8B-Instruct-2512 · Q3_K_S
Apple M5 Ultra512GBOllama v0.31L2 Cross-framework verified
This page aggregates 1 real-world runs of Ministral-3-8B-Instruct-2512 (Q3_K_S) on Apple M5 Ultra with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
125.07 tok/s
Decode
Decode speed
471.87 tok/s
Prefill
Prefill speed
0.18 s
TTFT
Time to first token
13.02 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
11 days ago
Last verified
Performance
- llama.cpp · Q5_K_M Decode 84.63 · Prefill 432.9 ·
- Ollama · Q3_K_S (current)Decode 125.07 · Prefill 471.87 ·
Core figures
- Decode (avg)
- 125.07 tok/s
- Prefill (avg)
- 471.87 tok/s
- TTFT (avg)
- 0.18 s
- VRAM (avg)
- 13.02 GB
- MTP acceptance rate
- —
- TTFB
- 1 GB
- Power draw
- 110.3 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Ministral-3-8B-Instruct-2512
- Quantization
- Q3_K_S
- Framework
- Ollama
- Version
- v0.31
- Context length
- 8192 tokens
- Batch size
- 256
- GPU layers
- 28
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M5 Ultra
- Nominal VRAM
- 512 GB
- Measured VRAM (avg)
- 13.02 GB
- OS
- macOS 26.1
- Power draw
- 110.3 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.31 · macOS 26.1 · 8192 ctx
125.07 tok/s
Decode
471.87 tok/s
Prefill
0.18 s
TTFT
13.02 GB
VRAM
—
MTP
110.3 W
Power draw
L2 batch seed 2026-10-24: Ollama on hw_id=29 running model_id=74 at Q3_K_S